outages.live
Live
CerebrasIncident · 2026-09-25 12:16 UTC

Partial Service Disruption

ResolvedOfficial update

The incident has been resolved

The latest update from Cerebras.

State

Resolved

Started

37 d ago

2026-09-25 12:16 UTC

Lasted

4 h 58 min

until 2026-09-25 17:14 UTC

Worst impact

Partial outage

Timeline

3 updates
12:1613:3114:4516:0017:14
Partial outageUpdate postedTimes in UTC

Investigating

1 h 25 min 28%

Monitoring

3 h 33 min 72%

Updates

Times in UTC

As posted by Cerebras

Resolved2026-09-25 17:14 UTC

The incident has been resolved

Monitoring2026-09-25 13:41 UTC

Services are back up. We are still investigating the root cause.

Investigating2026-09-25 12:16 UTC

Some features may be temporarily unavailable since UTC 10:54. We are currently working to resume normal service performance. We will provide further updates as we make progress.

Affected components

2
GPT-OSS-120BQwen-3.8-27b

Cerebras in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

2

Days with an incident

2

Median duration

2 h 29 min

This incident

2.0× the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

4 h 58 min
median 2 h 29 min
90 days agoToday

Other Cerebras incidents

All incidents

Cerebras·Resolved

Between 11:00 and 11:15 UTC users experienced partial degradation with Gemma-4-31B. Service has been restored.

Resolvedresolved 66 d ago

Follow Cerebras

Your coding agent knows when Cerebras is down, and tells you when a failure is theirs, not yours. You can also get Cerebras incidents in a feed reader or in Slack.

Prompt
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.

Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.

Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "cerebras" and tell me if Cerebras has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.

Paste this into any coding agent. It adds the server with its own MCP setup.

RSS
https://outages.cc/feed.xml?providers=cerebras
Slack
/feed subscribe https://outages.cc/feed.xml?providers=cerebras

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane